u64 counter;
} group_entry;
struct perf_callchain_entry *callchain = NULL;
- struct perf_tracepoint_record *tp;
+ struct perf_raw_record *raw = NULL;
int callchain_size = 0;
u64 time;
struct {
header.size += sizeof(u64);
}
- if (sample_type & PERF_SAMPLE_TP_RECORD) {
- tp = data->private;
- header.size += tp->size;
+ if (sample_type & PERF_SAMPLE_RAW) {
+ raw = data->raw;
+ if (raw)
+ header.size += raw->size;
}
ret = perf_output_begin(&handle, counter, header.size, nmi, 1);
}
}
- if (sample_type & PERF_SAMPLE_TP_RECORD)
- perf_output_copy(&handle, tp->record, tp->size);
+ if ((sample_type & PERF_SAMPLE_RAW) && raw)
+ perf_output_copy(&handle, raw->data, raw->size);
perf_output_end(&handle);
}
*/
struct perf_task_event {
- struct task_struct *task;
+ struct task_struct *task;
+ struct perf_counter_context *task_ctx;
struct {
struct perf_event_header header;
static void perf_counter_task_event(struct perf_task_event *task_event)
{
struct perf_cpu_context *cpuctx;
- struct perf_counter_context *ctx;
+ struct perf_counter_context *ctx = task_event->task_ctx;
cpuctx = &get_cpu_var(perf_cpu_context);
perf_counter_task_ctx(&cpuctx->ctx, task_event);
put_cpu_var(perf_cpu_context);
rcu_read_lock();
- /*
- * doesn't really matter which of the child contexts the
- * events ends up in.
- */
- ctx = rcu_dereference(current->perf_counter_ctxp);
+ if (!ctx)
+ ctx = rcu_dereference(task_event->task->perf_counter_ctxp);
if (ctx)
perf_counter_task_ctx(ctx, task_event);
rcu_read_unlock();
}
-static void perf_counter_task(struct task_struct *task, int new)
+static void perf_counter_task(struct task_struct *task,
+ struct perf_counter_context *task_ctx,
+ int new)
{
struct perf_task_event task_event;
return;
task_event = (struct perf_task_event){
- .task = task,
- .event = {
+ .task = task,
+ .task_ctx = task_ctx,
+ .event = {
.header = {
.type = new ? PERF_EVENT_FORK : PERF_EVENT_EXIT,
.misc = 0,
void perf_counter_fork(struct task_struct *task)
{
- perf_counter_task(task, 1);
+ perf_counter_task(task, NULL, 1);
}
/*
void perf_tpcounter_event(int event_id, u64 addr, u64 count, void *record,
int entry_size)
{
- struct perf_tracepoint_record tp = {
+ struct perf_raw_record raw = {
.size = entry_size,
- .record = record,
+ .data = record,
};
struct perf_sample_data data = {
.regs = get_irq_regs(),
.addr = addr,
- .private = &tp,
+ .raw = &raw,
};
if (!data.regs)
unsigned long flags;
if (likely(!child->perf_counter_ctxp)) {
- perf_counter_task(child, 0);
+ perf_counter_task(child, NULL, 0);
return;
}
* incremented the context's refcount before we do put_ctx below.
*/
spin_lock(&child_ctx->lock);
+ child->perf_counter_ctxp = NULL;
/*
* If this context is a clone; unclone it so it can't get
* swapped to another process while we're removing all
* won't get any samples after PERF_EVENT_EXIT. We can however still
* get a few PERF_EVENT_READ events.
*/
- perf_counter_task(child, 0);
-
- child->perf_counter_ctxp = NULL;
+ perf_counter_task(child, child_ctx, 0);
/*
* We can recurse on the same lock type through: